Fast hog feature computation based on CUDA

Histogram of oriented gradients (HOG) is one of the most popular descriptors used for pedestrian detection, but this descriptor has its own drawback. Like most sliding window algorithms it is very slow, making it unsuitable for many real-time applications. This paper proposes a parallel implementation of the HOG algorithm. It bases on CUDA (compute unified device architecture) platform that could use parallel computing of graphic processing unit (GPU). The time consumption of HOG running on the GPU and on the CPU is compared by experiments in this paper. The results demonstrate that the HOG on GPU performs better than the HOG running on CPU, and is approximate 10 times speedup.